Complementary methods for virtual screening and the elucidation of binding patterns: MOLPRINT 2D3D

1
Complementary methods for virtual screening and
the elucidation of binding patterns MOLPRINT
2D/3D

• Andreas Bender
• ab454_at_cam.ac.uk
• Unilever Centre for Molecular Science Informatics
  Cambridge University, UK

2
Outline

• Objective More efficient similarity searching of
  chemical databases
• New methods developed to detect molecules with
  similar biology One is based on connectivity
  (2D), the other on surface points (3D)
• Results Lead Discovery finding new drugs,
  finding new chemotypes
• Feature Discovering Binding Patterns

3
Substructure vs. Similarity Searching

• Substructure searching aims to detect molecules
  containing a particular subgraph / substructure
  exact matching desired (e.g. to detect toxic
  groups)
• Similarity searching aims to detect molecules
  with similar properties structures may
  (sometimes should!) be structurally different
• Here employed for activity detection virtual
  screening
• Literature Bender, A. and Glen, R.C. Molecular
  similarity a key technique in molecular
  informatics. Org. Biomol. Chem. 2004, 2, 3204
  3218.

4
Descriptor Choice
5
2D Environment around an atom (MOLPRINT 2D)

• E.g. 6-aminoquinoline

Assign Sybyl mol2 atom types Find
connections Find connections to
connections Create a tree down to n levels Create
a fingerprint for this atom
N2
Level 0 Level 1 Level 2
Car Car
Car, Car, Car
1
2
1
1
These features are created for every (heavy) atom
in the molecule (J. Chem. Inf. Comput. Sci. 2004,
44, 170-178 2004, 44, 1710-1718)
6
Feature Selection

• E.g. comparing faces first requires the
  identification of key features.
• How do we identify these?
• The same applies to molecules.

7
B) Information-Gain Feature Selection

• We wish to select the important features.
• To do this we calculate the entropy of the data
  as a whole and for each class.
• This is used to select those features with the
  highest discrimination, e.g. active and inactive
  molecules.

Information gain (to be maximized)
Entropy of the whole set
Entropy of subsets
8
Classification

• The next step is to identify which molecules
  belong to which class.
• To do this we use a Naïve Bayesian Classifer
  using the features (atom environments) we have
  identified as being important.

9
C) Naïve Bayesian Classifier (classification by
presumptive evidence)

• Include all selected features fi in calculation
  of
• Ratio gt 1 Class membership 1
• Ratio lt 1 Class membership 2
• F feature vector fifeature elements

active
inactive
Feature counts in datasets
10
Application lead discovery

• Database MDL Drug Data Report (MDDR)
• 957 ligands selected from MDDR
• 49 5HT3 Receptor antagonists,
• 40 Angiotensin Converting Enzyme inhib. (ACE),
• 111 HMG-Co-Reductase inhibitors (HMG),
• 134 PAF antagonists and
• 49 Thromboxane A2 antagonists (TXA2)
• 574 inactives
• Briem and Lessel, Perspect Drug Discov Des
  2000, 20, 245-264.
• Calculated Hit rate among ten nearest neighbours
  for each molecule

11
Comparison
Using Tanimoto Coefficient
Using Bayesian

• Bender, A., et al., Similarity searching of
  chemical databases using atom environment
  descriptors evaluation of performance (MOLPRINT
  2D). J. Chem. Inf. Comput. Sci. 2004 (44) 1708
  1718.

12
Combining Information in Molecules

• In this method, we can extend the approach by
  extracting from a set of molecules those features
  having the best information gain
• This can describe patterns in molecules much
  better than individual cases

13
Combining Information of 5 Actives
Bender, A., et al., Molecular Similarity
Searching using Atom Environments,
Information-Based Feature Selection and a Naïve
Bayesian Classifier. J. Chem. Inf. Comput. Sci.
2004 (44) 170 178.
14
Transformation to 3D MOLPRINT 3D

• Idea To develop an analogous translationally and
  rotationally invariant (TRI) descriptor based on
  surface points
• Advantage Switching from element atom types to
  interaction energies gives more general model
  than 2D (graph) approach
• In Addition Local Description hopefully less
  conformationally dependent
• Approach to Fingerprint Surfaces Tanimoto and
  other methods become applicable (until now mainly
  used for 2D fingerprints)
• Reference Bender, A. et al., J. Med. Chem.,
  2004, 47, 6569 6583 and IEEE SMC 2004
  proceedings

15
The Conformational Problem








16
3D Environment around a surface point solvent
accessible surface
Central Point (Layer 0)
Points in Layer 1

• Points in Layer 2

8Å
Etc.
17
Overall Performance Comparable to 2D methods, and
in addition
18
TXA2, Graph-based Descriptors
1
2
3
4
5
6
7
Very little diversity in heterocyclic systems
no patents, no money!
19
TXA2, 7 Hits among Top 10
1
2
3
4
5
6
7
20
Which features are selected for classification?

• Even if your classifier works, do the selected
  features make sense?
• Set of active vs. inactive molecules
• Information Gain calculated for each feature,
  those which are much more frequent among actives
  are suspicious and might constitute the
  pharmacophore
• Look at features from HMG and TXA2

21
Selected Features - HMG

• Binding Site HMG rigid lipophilic ring

22
HMG-15
23
TXA2
Yellow lipophilic side chains

• Yamamoto et al., J. Med. Chem. 1993 (36) 820

24
TXA2-7
25
Identification of Features

• (a) Not in binding conformation
• (b) In different conformations

26
Summary

• 2D Method
• Performs about as other 2D methods for single
  molecule searches
• Outperforms them by a large margin when combining
  information from multiple molecules (J. Chem.
  Inf. Comput. Sci., 2004, 44, 170-178 J. Chem.
  Inf. Comput. Sci., 2004, 44, 1710-1718.)
• 3D Method translationally and rotationally
  stable (invariant) combines high enrichment
  factors with scaffold hopping discovery of new
  chemotypes possible
• (J. Med. Chem., 2004, 47, 6569 - 6583)
• Features shown to correlate with binding patterns

27
Future Work

• Use more solid description of surface
  properties (COSMO descriptors instead of force
  field properties)
• Shape encoding
• Different machine learning approaches

28
Acknowledgements

• Robert C Glen (Unilever Centre, Cambridge, UK)
• Hamse Y. Mussa (Unilever Centre, Cambridge, UK)
• Stephan Reiling (Aventis, Bridgewater, USA)
• David Patterson (Tripos)
• Software
• GRID, CACTVS, gOpenMol many, many others
• Funding
• The Gates Cambridge Trust, Unilever, Tripos